End of training

README.md

@@ -1,12 +1,27 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: mobilebert_sa_GLUE_Experiment_data_aug_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.609947111472742
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_sa_GLUE_Experiment_data_aug_mnli
 
-This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on an unknown dataset.
+This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4320
-- Accuracy: 0.5798
+- Loss: 0.9046
+- Accuracy: 0.6099
 
 ## Model description
 

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 6.0,
+    "epoch_mm": 6.0,
+    "eval_accuracy": 0.6185430463576159,
+    "eval_accuracy_mm": 0.609947111472742,
+    "eval_loss": 0.8754788637161255,
+    "eval_loss_mm": 0.9046403169631958,
+    "eval_runtime": 23.7109,
+    "eval_runtime_mm": 23.7235,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 413.945,
+    "eval_samples_per_second_mm": 414.441,
+    "eval_steps_per_second": 3.247,
+    "eval_steps_per_second_mm": 3.246,
+    "train_loss": 0.5154089748909961,
+    "train_runtime": 345135.8954,
+    "train_samples": 8048562,
+    "train_samples_per_second": 1165.999,
+    "train_steps_per_second": 9.109
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "epoch_mm": 6.0,
+    "eval_accuracy": 0.6185430463576159,
+    "eval_accuracy_mm": 0.609947111472742,
+    "eval_loss": 0.8754788637161255,
+    "eval_loss_mm": 0.9046403169631958,
+    "eval_runtime": 23.7109,
+    "eval_runtime_mm": 23.7235,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 413.945,
+    "eval_samples_per_second_mm": 414.441,
+    "eval_steps_per_second": 3.247,
+    "eval_steps_per_second_mm": 3.246
+}

logs/events.out.tfevents.1676113740.glendale.185391.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a282d8537ab8205c7ee67d46a8c292e5da5d3f07405cde93186ade19fc43925
+size 698

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.5154089748909961,
+    "train_runtime": 345135.8954,
+    "train_samples": 8048562,
+    "train_samples_per_second": 1165.999,
+    "train_steps_per_second": 9.109
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.8754788637161255,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_data_aug_mnli/checkpoint-62880",
+  "epoch": 6.0,
+  "global_step": 377280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.9e-05,
+      "loss": 0.8429,
+      "step": 62880
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6185430463576159,
+      "eval_loss": 0.8754788637161255,
+      "eval_runtime": 22.822,
+      "eval_samples_per_second": 430.068,
+      "eval_steps_per_second": 3.374,
+      "step": 62880
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6713,
+      "step": 125760
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6038716250636781,
+      "eval_loss": 0.9512428045272827,
+      "eval_runtime": 23.3868,
+      "eval_samples_per_second": 419.682,
+      "eval_steps_per_second": 3.292,
+      "step": 125760
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5387,
+      "step": 188640
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5977585328578706,
+      "eval_loss": 1.0795714855194092,
+      "eval_runtime": 23.3576,
+      "eval_samples_per_second": 420.205,
+      "eval_steps_per_second": 3.297,
+      "step": 188640
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4297,
+      "step": 251520
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.596128374936322,
+      "eval_loss": 1.1877483129501343,
+      "eval_runtime": 23.3912,
+      "eval_samples_per_second": 419.602,
+      "eval_steps_per_second": 3.292,
+      "step": 251520
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3405,
+      "step": 314400
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5895058583800306,
+      "eval_loss": 1.3153903484344482,
+      "eval_runtime": 23.7344,
+      "eval_samples_per_second": 413.535,
+      "eval_steps_per_second": 3.244,
+      "step": 314400
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2693,
+      "step": 377280
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5798267957208355,
+      "eval_loss": 1.4319931268692017,
+      "eval_runtime": 23.7067,
+      "eval_samples_per_second": 414.018,
+      "eval_steps_per_second": 3.248,
+      "step": 377280
+    },
+    {
+      "epoch": 6.0,
+      "step": 377280,
+      "total_flos": 1.5141783163392492e+18,
+      "train_loss": 0.5154089748909961,
+      "train_runtime": 345135.8954,
+      "train_samples_per_second": 1165.999,
+      "train_steps_per_second": 9.109
+    }
+  ],
+  "max_steps": 3144000,
+  "num_train_epochs": 50,
+  "total_flos": 1.5141783163392492e+18,
+  "trial_name": null,
+  "trial_params": null
+}